Full index · agent skills
All agent skills - page 420 of 640
Every one of the 63,961 agent skills in the directory, ranked by adoption. Jump to a tool, or browse the agent skills hub.
- Ielts ExamHelps with ai & agent building tasks during AI-assisted development.30 installs
- ImagenHelps with ai & agent building tasks.30 installs
- Improve Codebase ArchitectureHelps with ai & agent building tasks.30 installs
- Incident ResponderGuides CSIRT security incident response: declaring and scoping incidents, timeline reconstruction, evidence preservation, containment coordination, and post-incident review.30 installs
- Information Systems Security Officer Classified SpecialistGuides ISSO work for classified systems: system security plan stewardship, control status and POA&M tracking, continuous monitoring, and authorization (ATO) packages.30 installs
- Infrastructure EngineerGuides cloud infrastructure design and implementation: IaC with Terraform/Pulumi, CI/CD pipelines, Kubernetes orchestration, networking, observability, and security hardening.30 installs
- Internal CommsHelps with ai & agent building tasks.30 installs
- JiraManage and search Jira Cloud issues via the REST API and JQL.30 installs
- Karpathy GuidelinesFollow Andrej Karpathy's best practices for LLM development and AI agent building30 installs
- Ktor PatternsBuild an Android network layer with Ktor, including error handling, DTO mapping, interceptors, and certificate pinning.30 installs
- LangchainBuild LLM applications like agents, chatbots, and RAG systems using chains, tool calling, memory, and 500+ integrations.30 installs
- Langsmith ObservabilityTrace, evaluate, and monitor LLM applications against datasets to debug outputs and run systematic testing pipelines.30 installs
- Laravel Migrations And FactoriesHelps with ai & agent building tasks.30 installs
- Laravel Rate LimitingHelps with ai & agent building tasks.30 installs
- Laravel Strategy PatternHelps with ai & agent building tasks.30 installs
- Laravel Template Method And PluginsHelps with ai & agent building tasks.30 installs
- Laravel Transactions And ConsistencyHelps with ai & agent building tasks.30 installs
- LlavaRun visual instruction tuning and image-based conversations by combining a CLIP vision encoder with LLaMA/Vicuna models.30 installs
- Macos Design GuidelinesDevelopers use this to improve their workflow when working with macos-design-guidelines.30 installs
- Make Skill Templatemake-skill-template skill for Claude30 installs
- Managing YoutrackInteracts with YouTrack via REST API to create, search, and update issues and drafts, manage comments/tags/links, log work, and inspect field schemas.30 installs
- McpHelps with ai & agent building tasks.30 installs
- MicrobenchmarkingHelps with ai & agent building tasks.30 installs
- Microservice ResearcherGuides research for microservices decisions: domain decomposition, service-boundary trade-offs, sync vs async patterns, data ownership, and strangler migration with decision records.30 installs
- MigrateHelps with ai & agent building tasks.30 installs
- Migrate Dotnet10 To Dotnet11Helps with ai & agent building tasks.30 installs
- Migrate Nullable ReferencesHelps with ai & agent building tasks.30 installs
- Mime Detection RoutingDetect file MIME types and route documents to appropriate handlers in Xberg pipeline30 installs
- Mission CriticalGuides mission-critical system framing: criticality tiering, availability/integrity/continuity objectives, blast-radius mapping, redundant architecture, and Tier 0/1 release governance.30 installs
- Ml Research Engineer SafeguardsGuides ML research for safeguards: safety classifier development, harm benchmarks and eval suites, dataset design, fine-tuning, calibration, and model-promotion criteria.30 installs
- Ml Systems Engineer Rl EngineeringGuides ML systems engineering for reinforcement learning: distributed training platforms, rollout workers, replay buffers, checkpointing, experiment tracking, and training reliability.30 installs
- Modal Serverless GpuRun ML workloads on serverless GPU cloud with on-demand access, model API deployment, and automatic scaling.30 installs
- Moe TrainingTrain Mixture-of-Experts models with DeepSpeed or HuggingFace to scale capacity without proportional compute.30 installs
- MoltycashPay humans in USDC from an AI agent by tipping, hiring, or posting a gig, settled via x402 on Base.30 installs
- Motion ScaleGenerates animation duration, easing, and delay tokens with prefers-reduced-motion support, output as CSS, Tailwind, or JSON.30 installs
- Nemo CuratorCurate LLM training data on GPUs with fuzzy and semantic deduplication, quality filtering, and PII redaction.30 installs
- Oauth Sso AttackHelps with security tasks during AI-assisted development.30 installs
- Obsidian CliUse when obsidian cli to optimize AI-coding tasks.30 installs
- Omega Claude CliHelps with ai & agent building tasks.30 installs
- Openapi GeneratorGenerate multi-language API clients and server stubs from OpenAPI specs using openapi-generator-cli and the Maven plugin, including Java clients and Spring servers.30 installs
- OpencontextRoute a project-memory request into one packet (load, search, store, or setup) so the next coding agent starts with the right context instead of cold.30 installs
- Optimizing Attention FlashSpeed up transformer attention 2-4x and cut memory 10-20x with Flash Attention for long sequences.30 installs
- Oracle DbaAdminister, tune, secure, and scale Oracle Autonomous Database on OCI, optionally via Oracle MCP servers.30 installs
- Oss PrAutomate OSS pull request workflow: branch creation, testing, commit, and PR creation30 installs
- OutlinesGuarantee valid JSON, XML, or code during generation using Pydantic models with local models like Transformers and vLLM.30 installs
- Parallel Code ReviewRuns multiple specialized review agents (security, architecture, performance) in parallel over a changeset, tracking decisions and producing one consolidated report.30 installs
- Peer ReviewHelps with ai & agent building tasks.30 installs
- Performing Security Code ReviewAudit a codebase for security vulnerabilities and get a report with severity and remediation before release.30 installs
- Pg BossHelps with ai & agent building tasks during AI-assisted development.30 installs
- Phoenix FrontendFollow Phoenix frontend conventions when building or refactoring React/TypeScript components, styles, and UI features in the app/ directory.30 installs
- Phoenix ObservabilityTrace, evaluate, and monitor LLM applications with OpenTelemetry-based spans, dataset experiments, and LLM-as-judge evaluators, self-hosted.30 installs
- PineconeStore and query vectors in Pinecone's managed serverless database with metadata filtering, namespaces, and hybrid dense-plus-sparse search for RAG.30 installs
- Platform EngineerGuides platform engineering: internal developer platforms, golden paths, paved-road templates, developer portals (Backstage), and multi-tenant Kubernetes platforms.30 installs
- Platform Specific Ad Copy GeneratorHelps with ai & agent building tasks during AI-assisted development.30 installs
- PlaywrightAutomate cross-browser E2E tests, scraping, and screenshots with Playwright in TypeScript.30 installs
- Playwright InteractiveHelps with ai & agent building tasks.30 installs
- Popup CroDesign or optimize an email-capture or exit-intent popup to convert visitors without hurting the experience.30 installs
- PortfoliosyncingSyncing broker CSV position exports (Fidelity) into a Google Sheets portfolio tracker without breaking its formulas.30 installs
- Pp PrintifyHelps with ai & agent building tasks during AI-assisted development.30 installs
- Pp Sncf ConnectHelps with ai & agent building tasks during AI-assisted development.30 installs
- Privacy Research Engineer SafeguardsGuides privacy research for AI safeguards: PII detection research, redaction/de-identification evals, memorization risk studies, and logging-minimization for safety pipelines.30 installs
- Product Infrastructure Security EngineerSecures product runtime and data plane: multi-tenant isolation, service-to-service auth, secure API/worker defaults, rate limits, product-scoped secrets, and security design reviews.30 installs
- Prompt EngineerDesign, test, and optimize LLM prompts: prompt patterns (few-shot, chain-of-thought, ReAct), system prompt design, output formatting, evaluation, and token optimization.30 installs
- Prompt GuardDetect prompt injection and jailbreak attempts in user input and third-party data using Meta's 86M Prompt Guard classifier before it reaches the LLM.30 installs
- Provider Test PatternsHelps with testing & qa tasks.30 installs
- Pubmed DatabaseHelps with databases tasks.30 installs
- Pw Cover ImageHelps with ai & agent building tasks.30 installs
- Pyvene InterventionsPerform causal interventions on PyTorch models with pyvene's declarative framework for activation patching, causal tracing, and interchange intervention training.30 installs
- Qodo Get Relevant RulesFetch code quality and linting rules30 installs
- Query OptimizationHelps with ai & agent building tasks.30 installs
- Rag BuilderHelps with ai & agent building tasks.30 installs
- Ray TrainOrchestrate distributed training across clusters with Ray Train, scaling PyTorch/TensorFlow/HuggingFace from a single GPU to many nodes with fault tolerance.30 installs
- React Server ComponentsBuild with React Server Components in the Next.js App Router: server vs client components, Server Actions, streaming, caching, and zero client-JS data fetching.30 installs
- Recommender SystemHelps with ai & agent building tasks.30 installs
- ReferenceHelps with ai & agent building tasks.30 installs
- Release NotesHelps with productivity & planning tasks.30 installs
- ResearchHelps with ai & agent building tasks.30 installs
- Research Engineer Scientist TokensGuides LLM token research: hypotheses on context use and tokenization, benchmarks for tokens-per-task and quality-cost Pareto, ablation design, and reproducible logs.30 installs
- Research GrantsHelps with ai & agent building tasks.30 installs
- RetroHelps with ai & agent building tasks.30 installs
- Revenue Model DesignChoose and design a revenue model: how money flows in, from whom, and on what cadence, including stacking streams.30 installs
- Robotics Automation Integration EngineerIntegrates and commissions robotic and factory automation cells: arms/cobots/AMRs, PLC/PC interfaces, safety wiring, industrial fieldbuses, vision-guided pick, and FAT/SAT.30 installs
- Role TestHelps with testing & qa tasks.30 installs
- Run EvalsRun OpenWork UI evaluation flows end-to-end against a real Electron app in a Daytona sandbox or local instance for comprehensive testing.30 installs
- Run TestsRun the Cartridge Controller test suites (unit, storybook visual regression, e2e, build) to validate changes.30 installs
- Rust TestingReference for Rust testing with cargo test, tokio-test, and mockall covering unit and integration tests, async testing, mocking, and benchmarks.30 installs
- Schema MarkupAdd or fix JSON-LD schema markup to enable rich results and improve search CTR.30 installs
- Scroll Stopping Hook GeneratorHelps with ai & agent building tasks during AI-assisted development.30 installs
- Search SpecialistHelps with ai & agent building tasks during AI-assisted development.30 installs
- Senior Revenue AccountantApplies ASC 606/IFRS 15 to revenue recognition and contract analysis: performance obligations, deferred revenue schedules, commission accounting, and revenue metrics (ARR, NRR).30 installs
- SentencepieceTrain and use language-independent BPE or Unigram tokenizers with SentencePiece on raw Unicode text for multilingual and CJK models.30 installs
- SeoHelps with marketing & seo tasks during AI-assisted development.30 installs
- Seo Content AuditorHelps with marketing & seo tasks during AI-assisted development.30 installs
- Shared ModelsDefine cross-platform KMP domain models with kotlinx.serialization, sealed state hierarchies, pagination models, and inline validation.30 installs
- SiwaAdd Sign-In With Agent (SIWA) authentication so ERC-8004 agents can authenticate to a service, with framework middleware for verification.30 installs
- Skill CreatorHelps with ai & agent building tasks.30 installs
- Skill NameHelps with ai & agent building tasks.30 installs
- Slf4jReference for SLF4J, the Java logging facade, covering parameterized logging, MDC support, and integration with Logback and Log4j2.30 installs
- Software Assurance Formal Methods SpecialistApply formal methods and software assurance to critical systems.30 installs
- Spec KitInstall GitHub spec-kit and run the constitution-to-implement pipeline so an executable spec drives a project across multiple AI agents.30 installs